Boeing Comput. Services, Seattle, WA.
IEEE Trans Image Process. 1995;4(10):1407-16. doi: 10.1109/83.465105.
Contour finding of distinct features in 2-D/3-D images is essential for image analysis and computer vision. To overcome the potential problems associated with existing contour finding algorithms, we propose a framework, called the neural network-based stochastic active contour model (NNS-SNAKE), which integrates a neural network classifier for systematic knowledge building, an active contour model (also known as the "Snake") for automated contour finding using energy functions, and the Gibbs sampler to help the snake to find the most probable contour using a stochastic decision mechanism. Successful application of the NNS-SNAKE to extraction of several types of contours on magnetic resonance (MR) images is presented.
二维/三维图像中显著特征的轮廓提取对于图像分析和计算机视觉至关重要。为了克服现有轮廓提取算法可能存在的问题，我们提出了一个框架，称为基于神经网络的随机主动轮廓模型（NNS-SNAKE），它集成了一个神经网络分类器，用于系统知识构建，一个主动轮廓模型（也称为“Snake”），用于使用能量函数自动提取轮廓，以及 Gibbs 采样器，用于通过随机决策机制帮助 Snake 找到最可能的轮廓。我们成功地将 NNS-SNAKE 应用于磁共振（MR）图像中几种类型的轮廓提取。
